Agent skill

Character Design Sheet Prompt

by Rylaispirit in Rylaispirit/cinematic-video-prompt-skill

Writes one image prompt for a 16:9 character reference sheet, with three full-body views and a face close-up, so a character stays consistent across AI video clips.

MITAuto-check passedMedia & Creative

SKILL.md written in Vietnamese; this summary is our English description.

Install Character Design Sheet Prompt

skills CLI
$ npx skills add Rylaispirit/cinematic-video-prompt-skill --skill character-sheet-lite -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Rylaispirit/cinematic-video-prompt-skill character-sheet-lite --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Rylaispirit/cinematic-video-prompt-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/bonus-skills/character-sheet-lite .claude/skills/character-sheet-lite && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
character-sheet-lite
GitHub stars
146
Token cost
~941 tokens
SKILL.md length
493 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Writes one image prompt for a 16:9 character reference sheet, with three full-body views and a face close-up, so a character stays consistent across AI video clips.

  • Works in 5 steps: Cách làm → 4 luật để nhân vật không "nhạt" → Khung prompt → …
  • Making a character reference sheet before generating AI video clips
  • SKILL.md covers 1. Cách làm, 2. 4 luật để nhân vật không…, 3. Khung prompt and 4. Theo công cụ, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill produces a single prompt that yields one 16:9 image: three full-body poses (front, side, back) on the left and a chest-up close-up of the face on the right. That image then serves as a reference so the character does not change face between video clips. The explanation to the user is short and in Vietnamese, while the prompt sent to the image model is written in English.

The agent takes a short character description, fills gaps with reasonable choices and states them as assumptions, and asks at most one question: which tool (Midjourney, Stable Diffusion or Flux) and whether the look is realistic or 3D animated. It fills a prompt template, then adds a character lock tag of 8 to 10 concrete keywords for reuse in later video prompts. Four rules keep the character from looking bland: a clear silhouette, mixed colors rather than basic ones with one strong accent, at least 2 signs of wear, and no empty praise words. Faces of real actors, celebrities or existing film and game characters are off limits.

Tool notes follow. Midjourney gets the --ar 16:9 and --style raw flags plus a --no list, Stable Diffusion gets a negative prompt, and Flux largely ignores negative prompts, so exclusions are written as positive statements in the main prompt.

When your agent uses it

  • Making a character reference sheet before generating AI video clips
  • Keeping a character's face and outfit consistent across several shots
  • Writing a Midjourney, Stable Diffusion or Flux prompt for a character design

Example prompts

  • “Make a character sheet prompt for a weathered lighthouse keeper, realistic style, for Midjourney.”
  • “I need a consistent 3D animated fox courier across ten video clips, so start with a design sheet.”
  • “Write a Flux prompt for a character reference sheet of a young street musician.”

Requirements

  • An image model such as Midjourney, Stable Diffusion or Flux to run the prompt

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Cách làm
  2. 4 luật để nhân vật không "nhạt"
  3. Khung prompt
  4. Theo công cụ
  5. Thẻ khóa nhân vật

What it can do on your machine

Read from SKILL.md and the folder at commit 389c193. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Character Design Sheet Prompt loads about 941 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 493 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~941

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Rylaispirit/cinematic-video-prompt-skill at commit 389c193, republished under its MIT licence (© Rylaispirit). 493 words, ~941 tokens.

Download SKILL.mdSave it as .claude/skills/character-sheet-lite/SKILL.md (or your agent's skills folder).
name
character-sheet-lite
description
Dùng khi cần prompt ảnh thiết kế nhân vật (3 góc toàn thân + cận mặt trong 1 ảnh) cho Midjourney/SD/Flux để giữ nhân vật nhất quán khi làm video AI. Bản Lite.

Character Sheet Lite — prompt bảng thiết kế nhân vật

Tạo 1 prompt cho ra 1 ảnh 16:9: bên trái 3 dáng toàn thân (trước / nghiêng / sau), bên phải 1 cận mặt từ ngực lên. Ảnh này dùng làm ảnh tham chiếu để nhân vật không "đổi mặt" giữa các clip video.

Giải thích cho người dùng bằng tiếng Việt, ngắn gọn. Prompt gửi model viết bằng tiếng Anh.

1. Cách làm

  1. Nhận mô tả nhân vật (vài dòng là đủ). Thiếu gì thì tự chọn hợp lý và ghi rõ giả định.
  2. Hỏi 1 câu nếu chưa biết: dùng Midjourney, SD hay Flux? Và muốn tả thực người thật hay 3D hoạt hình?
  3. Viết prompt theo khung ở mục 3, rồi thêm Thẻ khóa nhân vật (8–10 từ khóa) để nối vào prompt video sau này.

2. 4 luật để nhân vật không "nhạt"

  1. Hình bóng rõ: nhìn đường viền phải nhận ra (vai rất rộng, áo choàng lớn, dáng chữ A, chữ V...). Đừng chỉ là "một người mặc đồ".
  2. Màu pha, không màu cơ bản: viết charcoal violet, rust brown, faded indigo thay cho gray / brown / blue. Thêm 1 màu tương phản mạnh ở đúng 1 chỗ nhỏ (lớp lót, cúc áo, mống mắt).
  3. Có dấu vết sống: chọn ít nhất 2 thứ — vết vá, chỗ sờn, sẹo, bất đối xứng, bụi bẩn.
  4. Không từ rỗng: tránh beautiful, handsome, cool, stylish, pretty. Thay bằng mô tả cụ thể nhìn thấy được.

Nguyên bản bắt buộc: không lấy mặt diễn viên, ngôi sao hay nhân vật phim/game có sẵn. Nếu người dùng muốn "giống X" thì đề xuất thiết kế nguyên bản thay thế.

3. Khung prompt

character design reference sheet, single image, left: three full-body views (front, side profile, back) in a row, A-pose, evenly spaced; right: one large chest-up close-up headshot,
[gender], [age] years old, [build], [skin tone with undertone],
face: [face shape, eyes + iris color, brows, nose, lips], natural asymmetry, visible skin texture, [one mark: scar / mole / freckles], default expression [mood],
hair: [length, texture, multi-tone color, styling],
wearing: [inner layer: fabric + color], [outer layer: fabric + color + silhouette], [one sign of wear], [one accent color detail],
footwear: [style + material + wear], accessories: [1 item with a story],
[render style: cinematic 3D character / photoreal film still / stylized], same identity across all views, same outfit, studio lighting, neutral light gray background, no text, no labels, no watermark, ultra detailed
Show full SKILL.md (208 more words)Show less

4. Theo công cụ

  • Midjourney: thêm --ar 16:9 --style raw, loại trừ bằng --no text, watermark, plastic skin, extra fingers, celebrity likeness.
  • Stable Diffusion: dùng ô prompt âm: inconsistent face, outfit changes between views, plastic skin, airbrushed, bad anatomy, extra fingers, text, watermark, celebrity likeness, cropped.
  • Flux: gần như bỏ qua prompt âm → viết thành câu khẳng định trong prompt chính (vd "no text anywhere, skin with visible pores").

5. Thẻ khóa nhân vật

8–10 từ khóa ngắn, cụ thể, nhìn thấy được. Ví dụ: woman early 30s, lean build, crooked nose, olive skin, scar through left brow, ash-black bob, faded indigo wrap coat, rust silk lining, scuffed leather boots, brass ring on thumb

Nối thẻ này vào mọi prompt cảnh/video có nhân vật, kèm ảnh sheet làm ảnh tham chiếu.


Bản Full (VIP) có thêm: quy trình bảng tổng thiết kế nhiều nhân vật, 6 luật cực đoan hóa đầy đủ, kho 20 phong cách render + 9 ngôn ngữ cắt may, hướng dẫn trang phục 3 lớp và 5 chiều chất vải, hướng dẫn khuôn mặt theo tuổi và theo vùng da, bảng tra tiếng Anh cho chất vải và nét mặt, kiểm soát 4000 ký tự, checklist 17 mục. Liên hệ tác giả qua GitHub @Rylaispirit.

© Rylaispirit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in bonus-skills/character-sheet-lite of Rylaispirit/cinematic-video-prompt-skill.

Open the folder on GitHubat commit 389c193

Compare with similar skills

Character Design Sheet Prompt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Character Design Sheet Prompt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Character Design Sheet Prompt this skillRylaispirit/cinematic-video-prompt-skill146—~941Automated safety check: PassMIT
AI Image Prompts SkillLeoYeAI/openclaw-master-skills2.2k—~4.3kAutomated safety check: PassMIT
Prompt EngineAgriciDaniel/claude-prompts110—~1.2kAutomated safety check: PassMIT
Image Prompt Engineeringrevfactory/harness-1001.3k—~1.2kAutomated safety check: PassApache-2.0
Image to Prompt Reverse Engineeringwuyoscar/GPT-Image2-Skill5.6k—~1.8kAutomated safety check: PassMIT
GPT Image 2 Prompt and GenerationConardLi/garden-skills13k—~4kAutomated safety check: NotesMIT

Similar skills

  • AI Image Prompts Skill

    LeoYeAI/openclaw-master-skills

    Recommend curated prompts from a 10,000+ real-world image generation prompt library.

    2.2k GitHub stars~4.3k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Prompt Engine

    AgriciDaniel/claude-prompts

    Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram…

    110 GitHub stars~1.2k tokensUpdated 5 mo ago
    AI & LLM EngineeringAuto-check passed
  • Image Prompt Engineering

    revfactory/harness-100

    AI Image (Gemini/DALL-E/Midjourney) Prompt Writing Guide. An agent skill from revfactory/harness-100.

    1.3k GitHub stars~1.2k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed
  • Image to Prompt Reverse Engineering

    wuyoscar/GPT-Image2-Skill

    Analyzes a reference image and writes a prompt that could recreate it in an AI image generator, focusing on the visual traits that most affect similarity.

    5.6k GitHub stars~1.8k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • GPT Image 2 Prompt and Generation

    ConardLi/garden-skills

    Generates or edits images with GPT Image 2 through an OpenAI-compatible API, or falls back to writing finished prompts from a library of structured templates.

    13k GitHub stars~4k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Qwen Edit

    digitalsamba/claude-code-video-toolkit

    AI image editing prompting patterns for Qwen-Image-Edit. An agent skill from digitalsamba/claude-code-video-toolkit.

    2.2k GitHub starsUsed in 1 repo~711 tokens
    Media & CreativeAuto-check passed

More from Rylaispirit/cinematic-video-prompt-skill

  • Cinematic Video Prompt Guide

    Rylaispirit/cinematic-video-prompt-skill

    Acts as a cinematography dictionary and prompt formula for writing AI video and image prompts about camera angles, movement, lighting and mood.

    146 GitHub stars~5k tokensUpdated 9 days ago
    Auto-check passed
  • Oriental Scene Lite

    Rylaispirit/cinematic-video-prompt-skill

    Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo.

    146 GitHub stars~858 tokensUpdated 9 days ago
    Auto-check passed

Works with

Questions about Character Design Sheet Prompt

What does Character Design Sheet Prompt do?

Writes one image prompt for a 16:9 character reference sheet, with three full-body views and a face close-up, so a character stays consistent across AI video clips. The skill produces a single prompt that yields one 16:9 image: three full-body poses (front, side, back) on the left and a chest-up close-up of the face on the right. That image then serves as a reference so the character does not change face between video clips.

When should I use Character Design Sheet Prompt?

Character Design Sheet Prompt fits situations like: making a character reference sheet before generating AI video clips; keeping a character's face and outfit consistent across several shots; writing a Midjourney, Stable Diffusion or Flux prompt for a character design.

How do I install Character Design Sheet Prompt in Claude Code?

Run `npx skills add Rylaispirit/cinematic-video-prompt-skill --skill character-sheet-lite -a claude-code`. Or copy the skill folder (bonus-skills/character-sheet-lite in Rylaispirit/cinematic-video-prompt-skill) into .claude/skills/character-sheet-lite in your project. Claude Code loads it when a task matches its description.

How do I install Character Design Sheet Prompt in Codex?

Run `npx skills add Rylaispirit/cinematic-video-prompt-skill --skill character-sheet-lite -a codex`. Or copy the skill folder (bonus-skills/character-sheet-lite in Rylaispirit/cinematic-video-prompt-skill) into .agents/skills/character-sheet-lite in your project. Codex loads it when a task matches its description.

Can I use Character Design Sheet Prompt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Rylaispirit/cinematic-video-prompt-skill --skill character-sheet-lite -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/character-sheet-lite, .gemini/skills/character-sheet-lite, .github/skills/character-sheet-lite and .opencode/skills/character-sheet-lite in your project.

What does Character Design Sheet Prompt need to run?

SKILL.md names no scripts, command-line tools or credentials: Character Design Sheet Prompt is instructions for the agent only. Our summary lists: An image model such as Midjourney, Stable Diffusion or Flux to run the prompt.

Does Character Design Sheet Prompt access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Character Design Sheet Prompt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Character Design Sheet Prompt use?

Character Design Sheet Prompt is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Character Design Sheet Prompt use?

About 941 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Character Design Sheet Prompt?

Skills that share tags, products or a category with Character Design Sheet Prompt: AI Image Prompts Skill (LeoYeAI/openclaw-master-skills, 2.2k stars), Prompt Engine (AgriciDaniel/claude-prompts, 110 stars), Image Prompt Engineering (revfactory/harness-100, 1.3k stars) and Image to Prompt Reverse Engineering (wuyoscar/GPT-Image2-Skill, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Character Design Sheet Prompt?

Rylaispirit (a GitHub user) maintains it in Rylaispirit/cinematic-video-prompt-skill, which has 146 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 27, 2026.

Source: Rylaispirit/cinematic-video-prompt-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.